Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6228. Min Range: -2.6228

Max Act: 2.6228. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 2.6228. Min Range: -2.6228

Max Act: 2.6071. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 2.6228. Min Range: -2.6228

Max Act: 2.3911. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.9658. Min Act: -0.0000

Data Index: 369720 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.9144. Min Act: -0.0000

Data Index: 945047 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.9087. Min Act: -0.0000

Data Index: 1366317 (Python Code)

Max Activating Token Index: 511

Text #6

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.9276. Min Act: -0.0000

Data Index: 1474591 (Python Code)

Max Activating Token Index: 662

Text #7

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8261. Min Act: -0.0000

Data Index: 792040 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8483. Min Act: -0.0000

Data Index: 1364285 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8990. Min Act: -0.0000

Data Index: 1645406 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8317. Min Act: -0.0000

Data Index: 1629499 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8932. Min Act: -0.0000

Data Index: 1502771 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8310. Min Act: -0.0000

Data Index: 1516231 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.8204. Min Act: -0.0000

Data Index: 1503128 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.7858. Min Act: -0.0000

Data Index: 1493692 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1418036 (Python Code)

Max Activating Token Index: 608

Text #16

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.7616. Min Act: -0.0000

Data Index: 1401719 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.7374. Min Act: -0.0000

Data Index: 1626821 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.6676. Min Act: -0.0000

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 2.6228. Min Range: -2.6228

Max Act: 1.7224. Min Act: -0.0000

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 959